EQ-Robin: Generating Multiple Minimal Unique-Cause MC/DC Test Suites
Robin Lee, Youngho Nam
公開日: 2025/9/30
Abstract
Modified Condition/Decision Coverage (MC/DC), particularly its strict Unique-Cause form, is a cornerstone of safety-critical software verification. A recent algorithm, "Robin's Rule," introduced a deterministic method to construct the theoretical minimum of N+1 test cases for Singular Boolean Expressions (SBEs). However, this approach yields only a single test suite, introducing a critical risk: if a test case forming a required 'independence pair' is an illegal input forbidden by system constraints, the suite fails to achieve 100% coverage. This paper proposes EQ-Robin, a lightweight pipeline that systematically generates a family of minimal Unique-Cause MC/DC suites to mitigate this risk. We introduce a method for systematically generating semantically equivalent SBEs by applying algebraic rearrangements to an Abstract Syntax Tree (AST) representation of the expression. By applying Robin's Rule to each structural variant, a diverse set of test suites can be produced. This provides a resilient path to discovering a valid test suite that preserves the N+1 minimality guarantee while navigating real-world constraints. We outline an evaluation plan on TCAS-II-derived SBEs to demonstrate how EQ-Robin offers a practical solution for ensuring robust MC/DC coverage.